Dual-path RNN: Efficient Long Sequence Modeling For Time-domain Single-channel Speech Separation

Abstract

Recent studies in deep learning-based speech separation have proven the superiority of time-domain approaches to conventional time-frequency-based methods. Unlike the time-frequency domain approaches, the time-domain separation systems often receive input sequences consisting of a huge number of time steps, which introduces challenges for modeling extremely long sequences. Conventional recurrent neural networks (RNNs) are not effective for modeling such long sequences due to optimization difficulties, while one-dimensional convolutional neural networks (1-D CNNs) cannot perform utterance-level sequence modeling when its receptive field is smaller than the sequence length. In this paper, we propose dual-path recurrent neural network (DPRNN), a simple yet effective method for organizing RNN layers in a deep structure to model extremely long sequences. DPRNN splits the long sequential input into smaller chunks and applies intra- and inter-chunk operations iteratively, where the input leng

Stats

• citations641
• S2 citations—
• github stars0
• HF likes0
• heat score21.06
• arxiv keyluo2019dual

Related papers

• Multi-path RNN For Hierarchical Modeling Of Long Sequential Data And Its Application To Speaker Stream Separation (2020)7.16
• DPCRN: Dual-path Convolution Recurrent Network For Single Channel Speech Enhancement (2021)14.35
• Embedding Recurrent Layers With Dual-path Strategy In A Variant Of Convolutional Network For Speaker-independent Speech Separation (2022)4.52
• Dual-path Filter Network: Speaker-aware Modeling For Speech Separation (2021)3.58
• Lafurca: Iterative Refined Speech Separation Based On Context-aware Dual-path Parallel Bi-lstm (2020)0.00
• Multi-loss Convolutional Network With Time-frequency Attention For Speech Enhancement (2023)0.00
• Dual-path Transformer Network: Direct Context-aware Modeling For End-to-end Monaural Speech Separation (2020)18.24
• Speech Separation Using An Asynchronous Fully Recurrent Convolutional Neural Network (2021)0.00